Toward building lightweight intrusion detection system through modified RMHC and SVM

Feature selection attracted much interest from researchers in many fields such as network security, pattern recognition and data mining. In this paper, we present a wrapper-based feature selection algorithm aiming at modeling lightweight intrusion detection system (IDS) by (1) using modified random mutation hill climbing (MRMHC) as search strategy to specify a candidate subset for evaluation; (2) using support vector machines (SVMs) as wrapper approach to obtain the optimum feature subset. We have examined the feasibility of our feature selection algorithm by conducting several experiments on KDD 1999 intrusion detection dataset which was categorized as DOS, PROBE, R2L, and U2R. The experimental results show that our approach is able not only to speed up the process of selecting important features but also to guarantee high detection rates. Furthermore, our experiments indicate that intrusion detection system with a combination of our proposed approach has smaller computational resources than that with GA-SVM which is a popular feature selection algorithm in the field.